Baltus Simon C, Geitenbeek Ritch T J, Frieben Maike, Thibeau-Sutre Elina, Wolterink Jelmer M, Tan Can O, Vermeulen Matthijs C, Consten Esther C J, Broeders Ivo A M J
Surgery Department, Meander Medical Centre, Maatweg, Amersfoort, 3818 TZ, Utrecht, The Netherlands.
Robotics and Mechatronics, University of Twente, Drienerlolaan, Enschede, 5722 NB, Overijssel, The Netherlands.
Surg Endosc. 2025 Mar;39(3):1536-1543. doi: 10.1007/s00464-024-11485-4. Epub 2025 Jan 3.
Specific pelvic bone dimensions have been identified as predictors of total mesorectal excision (TME) difficulty and outcomes. However, manual measurement of these dimensions (pelvimetry) is labor intensive and thus, anatomic criteria are not included in the pre-operative difficulty assessment. In this work, we propose an automated workflow for pelvimetry based on pre-operative magnetic resonance imaging (MRI) volumes.
We implement a deep learning-based framework to measure the predictive pelvic dimensions automatically. A 3D U-Net takes a sagittal T2-weighted MRI volume as input and determines five anatomic landmark locations: promontorium, S3-vertebrae, coccyx, dorsal, and cranial part of the os pubis. The landmarks are used to quantify the lengths of the pelvic inlet, outlet, depth, and the angle of the sacrum. For the development of the network, we used MRI volumes from 1707 patients acquired in eight TME centers. The automated landmark localization and pelvic dimensions measurements are assessed by comparison with manual annotation.
A center-stratified fivefold cross-validation showed a mean landmark localization error of 5.6 mm. The inter-observer variation for manual annotation was 3.7 ± 8.4 mm. The automated dimension measurements had a Spearman correlation coefficient ranging between 0.7 and 0.87.
To our knowledge, this is the first study to automate pelvimetry in MRI volumes using deep learning. Our framework can measure the pelvic dimensions with high accuracy, enabling the extraction of metrics that facilitate a pre-operative difficulty assessment of the TME.
特定的骨盆骨尺寸已被确定为全直肠系膜切除术（TME）难度和手术结果的预测指标。然而，手动测量这些尺寸（骨盆测量）劳动强度大，因此术前难度评估中未纳入解剖学标准。在这项研究中，我们提出了一种基于术前磁共振成像（MRI）容积的骨盆测量自动化工作流程。
我们实现了一个基于深度学习的框架来自动测量预测性骨盆尺寸。一个3D U-Net以矢状面T2加权MRI容积作为输入，并确定五个解剖标志点的位置：岬、S3椎体、尾骨、耻骨的背侧和头侧部分。这些标志点用于量化骨盆入口、出口的长度、深度以及骶骨的角度。为了开发该网络，我们使用了来自八个TME中心的1707例患者的MRI容积。通过与手动标注进行比较来评估自动标志点定位和骨盆尺寸测量。
中心分层的五重交叉验证显示，标志点定位的平均误差为5.6毫米。手动标注的观察者间差异为3.7±8.4毫米。自动尺寸测量的斯皮尔曼相关系数在0.7至0.87之间。
据我们所知，这是第一项使用深度学习对MRI容积中的骨盆测量进行自动化的研究。我们的框架能够高精度地测量骨盆尺寸，从而能够提取有助于TME术前难度评估的指标。
